Merge tag 'nfs-for-6.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Add a 'noalignwrite' mount option for lock-less 'lost writes' prevention
   - Add support for the LOCALIO protocol extention

  Bugfixes:
   - Fix memory leak in error path of nfs4_do_reclaim()
   - Simplify and guarantee lock owner uniqueness
   - Fix -Wformat-truncation warning
   - Fix folio refcounts by using folio_attach_private()
   - Fix failing the mount system call when the server is down
   - Fix detection of "Proxying of Times" server support

  Cleanups:
   - Annotate struct nfs_cache_array with __counted_by()
   - Remove unnecessary NULL checks before kfree()
   - Convert RPC_TASK_* constants to an enum
   - Remove obsolete or misleading comments and declerations"

* tag 'nfs-for-6.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (41 commits)
  nfs: Fix `make htmldocs` warnings in the localio documentation
  nfs: add "NFS Client and Server Interlock" section to localio.rst
  nfs: add FAQ section to Documentation/filesystems/nfs/localio.rst
  nfs: add Documentation/filesystems/nfs/localio.rst
  nfs: implement client support for NFS_LOCALIO_PROGRAM
  nfs/localio: use dedicated workqueues for filesystem read and write
  pnfs/flexfiles: enable localio support
  nfs: enable localio for non-pNFS IO
  nfs: add LOCALIO support
  nfs: pass struct nfsd_file to nfs_init_pgio and nfs_init_commit
  nfsd: implement server support for NFS_LOCALIO_PROGRAM
  nfsd: add LOCALIO support
  nfs_common: prepare for the NFS client to use nfsd_file for LOCALIO
  nfs_common: add NFS LOCALIO auxiliary protocol enablement
  SUNRPC: replace program list with program array
  SUNRPC: add svcauth_map_clnt_to_svc_cred_local
  SUNRPC: remove call_allocate() BUG_ONs
  nfsd: add nfsd_serv_try_get and nfsd_serv_put
  nfsd: add nfsd_file_acquire_local()
  nfsd: factor out __fh_verify to allow NULL rqstp to be passed
  ...

8 files changed, 149 insertions, 14 deletions

diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index ceb70a926b95..9ad727ddfedb 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -8,11 +8,20 @@
 #ifndef _LINUX_NFS_H
 #define _LINUX_NFS_H
 
+#include <linux/cred.h>
+#include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/string.h>
 #include <linux/crc32.h>
 #include <uapi/linux/nfs.h>
 
+/* The LOCALIO program is entirely private to Linux and is
+ * NOT part of the uapi.
+ */
+#define NFS_LOCALIO_PROGRAM		400122
+#define LOCALIOPROC_NULL		0
+#define LOCALIOPROC_UUID_IS_LOCAL	1
+
 /*
  * This is the kernel NFS client file handle representation
  */
diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h
new file mode 100644
index 000000000000..5fc02df88252
--- /dev/null
+++ b/include/linux/nfs_common.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file contains constants and methods used by both NFS client and server.
+ */
+#ifndef _LINUX_NFS_COMMON_H
+#define _LINUX_NFS_COMMON_H
+
+#include <linux/errno.h>
+#include <uapi/linux/nfs.h>
+
+/* Mapping from NFS error code to "errno" error code. */
+#define errno_NFSERR_IO EIO
+
+int nfs_stat_to_errno(enum nfs_stat status);
+int nfs4_stat_to_errno(int stat);
+
+#endif /* _LINUX_NFS_COMMON_H */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 1df86ab98c77..853df3fcd4c2 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -8,6 +8,7 @@
 #include <linux/wait.h>
 #include <linux/nfs_xdr.h>
 #include <linux/sunrpc/xprt.h>
+#include <linux/nfslocalio.h>
 
 #include <linux/atomic.h>
 #include <linux/refcount.h>
@@ -49,6 +50,7 @@ struct nfs_client {
 #define NFS_CS_DS		7		/* - Server is a DS */
 #define NFS_CS_REUSEPORT	8		/* - reuse src port on reconnect */
 #define NFS_CS_PNFS		9		/* - Server used for pnfs */
+#define NFS_CS_LOCAL_IO		10		/* - client is local */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
@@ -125,6 +127,13 @@ struct nfs_client {
 	struct net		*cl_net;
 	struct list_head	pending_cb_stateids;
 	struct rcu_head		rcu;
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	struct timespec64	cl_nfssvc_boot;
+	seqlock_t		cl_boot_lock;
+	nfs_uuid_t		cl_uuid;
+	spinlock_t		cl_localio_lock;
+#endif /* CONFIG_NFS_LOCALIO */
 };
 
 /*
@@ -158,6 +167,7 @@ struct nfs_server {
 #define NFS_MOUNT_WRITE_WAIT		0x02000000
 #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
 #define NFS_MOUNT_SHUTDOWN			0x08000000
+#define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
 
 	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
@@ -234,8 +244,7 @@ struct nfs_server {
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;
 #endif
-	struct ida		openowner_id;
-	struct ida		lockowner_id;
+	atomic64_t		owner_ctr;
 	struct list_head	state_owners_lru;
 	struct list_head	layouts;
 	struct list_head	delegations;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 45623af3e7b8..12d8e47bc5a3 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -446,7 +446,7 @@ struct nfs42_clone_res {
 
 struct stateowner_id {
 	__u64	create_time;
-	__u32	uniquifier;
+	__u64	uniquifier;
 };
 
 struct nfs4_open_delegation {
@@ -1854,6 +1854,24 @@ struct nfs_rpc_ops {
 };
 
 /*
+ * Helper functions used by NFS client and/or server
+ */
+static inline void encode_opaque_fixed(struct xdr_stream *xdr,
+				       const void *buf, size_t len)
+{
+	WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
+}
+
+static inline int decode_opaque_fixed(struct xdr_stream *xdr,
+				      void *buf, size_t len)
+{
+	ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
+	if (unlikely(ret < 0))
+		return -EIO;
+	return 0;
+}
+
+/*
  * Function vectors etc. for the NFS client
  */
 extern const struct nfs_rpc_ops	nfs_v2_clientops;
@@ -1866,4 +1884,4 @@ extern const struct rpc_version nfs_version4;
 extern const struct rpc_version nfsacl_version3;
 extern const struct rpc_program nfsacl_program;
 
-#endif
+#endif /* _LINUX_NFS_XDR_H */
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
new file mode 100644
index 000000000000..b353abe00357
--- /dev/null
+++ b/include/linux/nfslocalio.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+#ifndef __LINUX_NFSLOCALIO_H
+#define __LINUX_NFSLOCALIO_H
+
+/* nfsd_file structure is purposely kept opaque to NFS client */
+struct nfsd_file;
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/uuid.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svcauth.h>
+#include <linux/nfs.h>
+#include <net/net_namespace.h>
+
+/*
+ * Useful to allow a client to negotiate if localio
+ * possible with its server.
+ *
+ * See Documentation/filesystems/nfs/localio.rst for more detail.
+ */
+typedef struct {
+	uuid_t uuid;
+	struct list_head list;
+	struct net __rcu *net; /* nfsd's network namespace */
+	struct auth_domain *dom; /* auth_domain for localio */
+} nfs_uuid_t;
+
+void nfs_uuid_begin(nfs_uuid_t *);
+void nfs_uuid_end(nfs_uuid_t *);
+void nfs_uuid_is_local(const uuid_t *, struct list_head *,
+		       struct net *, struct auth_domain *, struct module *);
+void nfs_uuid_invalidate_clients(struct list_head *list);
+void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid);
+
+/* localio needs to map filehandle -> struct nfsd_file */
+extern struct nfsd_file *
+nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *,
+		   const struct cred *, const struct nfs_fh *,
+		   const fmode_t) __must_hold(rcu);
+
+struct nfsd_localio_operations {
+	bool (*nfsd_serv_try_get)(struct net *);
+	void (*nfsd_serv_put)(struct net *);
+	struct nfsd_file *(*nfsd_open_local_fh)(struct net *,
+						struct auth_domain *,
+						struct rpc_clnt *,
+						const struct cred *,
+						const struct nfs_fh *,
+						const fmode_t);
+	void (*nfsd_file_put_local)(struct nfsd_file *);
+	struct file *(*nfsd_file_file)(struct nfsd_file *);
+} ____cacheline_aligned;
+
+extern void nfsd_localio_ops_init(void);
+extern const struct nfsd_localio_operations *nfs_to;
+
+struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
+		   struct rpc_clnt *, const struct cred *,
+		   const struct nfs_fh *, const fmode_t);
+
+#else   /* CONFIG_NFS_LOCALIO */
+static inline void nfsd_localio_ops_init(void)
+{
+}
+#endif  /* CONFIG_NFS_LOCALIO */
+
+#endif  /* __LINUX_NFSLOCALIO_H */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 0c77ba488bba..fec1e8a1570c 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -151,13 +151,15 @@ struct rpc_task_setup {
 #define RPC_WAS_SENT(t)		((t)->tk_flags & RPC_TASK_SENT)
 #define RPC_IS_MOVEABLE(t)	((t)->tk_flags & RPC_TASK_MOVEABLE)
 
-#define RPC_TASK_RUNNING	0
-#define RPC_TASK_QUEUED		1
-#define RPC_TASK_ACTIVE		2
-#define RPC_TASK_NEED_XMIT	3
-#define RPC_TASK_NEED_RECV	4
-#define RPC_TASK_MSG_PIN_WAIT	5
-#define RPC_TASK_SIGNALLED	6
+enum {
+	RPC_TASK_RUNNING,
+	RPC_TASK_QUEUED,
+	RPC_TASK_ACTIVE,
+	RPC_TASK_NEED_XMIT,
+	RPC_TASK_NEED_RECV,
+	RPC_TASK_MSG_PIN_WAIT,
+	RPC_TASK_SIGNALLED,
+};
 
 #define rpc_test_and_set_running(t) \
 				test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index c419a61f60e5..e68fecf6eab5 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -67,9 +67,10 @@ enum {
  * We currently do not support more than one RPC program per daemon.
  */
 struct svc_serv {
-	struct svc_program *	sv_program;	/* RPC program */
+	struct svc_program *	sv_programs;	/* RPC programs */
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
+	unsigned int		sv_nprogs;	/* Number of sv_programs */
 	unsigned int		sv_nrthreads;	/* # of server threads */
 	unsigned int		sv_maxconn;	/* max connections allowed or
 						 * '0' causing max to be based
@@ -360,10 +361,9 @@ struct svc_process_info {
 };
 
 /*
- * List of RPC programs on the same transport endpoint
+ * RPC program - an array of these can use the same transport endpoint
  */
 struct svc_program {
-	struct svc_program *	pg_next;	/* other programs (same xprt) */
 	u32			pg_prog;	/* program number */
 	unsigned int		pg_lovers;	/* lowest version */
 	unsigned int		pg_hivers;	/* highest version */
@@ -441,6 +441,7 @@ bool		   svc_rqst_replace_page(struct svc_rqst *rqstp,
 void		   svc_rqst_release_pages(struct svc_rqst *rqstp);
 void		   svc_exit_thread(struct svc_rqst *);
 struct svc_serv *  svc_create_pooled(struct svc_program *prog,
+				     unsigned int nprog,
 				     struct svc_stat *stats,
 				     unsigned int bufsize,
 				     int (*threadfn)(void *data));
diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 63cf6fb26dcc..2e111153f7cd 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -14,6 +14,7 @@
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/gss_api.h>
+#include <linux/sunrpc/clnt.h>
 #include <linux/hash.h>
 #include <linux/stringhash.h>
 #include <linux/cred.h>
@@ -157,6 +158,10 @@ extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp);
 extern int	svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops);
 extern void	svc_auth_unregister(rpc_authflavor_t flavor);
 
+extern void	svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt,
+						   const struct cred *,
+						   struct svc_cred *);
+
 extern struct auth_domain *unix_domain_find(char *name);
 extern void auth_domain_put(struct auth_domain *item);
 extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new);